Jet printing ink drop point error prediction method

An error prediction and ink droplet technology, which is applied in the field of inkjet printing, can solve the problem of low efficiency of drop point error prediction, achieve the effect of strengthening overall and local optimization capabilities, maintaining diversity, and improving diversity and ergodicity

Pending Publication Date: 2022-05-31
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the defects and improvement needs of the prior art, the present invention provides a method for predicting the drop point error of jet printing ink, the purpose of which is to solve the problem of low prediction efficiency due to the drop point error obtained through direct measurement

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Jet printing ink drop point error prediction method
  • Jet printing ink drop point error prediction method
  • Jet printing ink drop point error prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] A LSTM neural network model construction method for jet printing ink drop point error prediction, such as figure 1 As shown, it includes: determining the network structure of the LSTM neural network model, using the improved dual particle swarm optimization algorithm to optimize the hyperparameters of the network structure, and using the training sample set to train the hyperparameter optimized network structure, and obtaining the ink used for jet printing. The LSTM neural network model of drop point error prediction; the optimization mode of described hyperparameter is:

[0060] S1. Set and initialize the main particle swarm and the auxiliary particle swarm, including initializing the dimensions and scales of each swarm, as well as the initial velocity and initial position of each particle, where each particle represents the hyperparameter set of the network structure; set fitness function, and calculate the fitness value of each particle to determine the initial indiv...

Embodiment 2

[0136] A method for predicting an ink drop point error in jet printing, comprising:

[0137] Collect the flight characteristic data of the ink droplet to be predicted, input the LSTM neural network model constructed by a kind of LSTM neural network model construction method for jet printing ink drop point error prediction as described in the first embodiment, the model outputs the jet printing Ink drop point error, to complete the prediction of jet printing ink drop point error.

[0138] The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

Embodiment 3

[0140] A computer-readable storage medium, the computer-readable storage medium includes a stored computer program, wherein when the computer program is run by a processor, the device where the storage medium is located is controlled to execute the above-mentioned one for spraying An LSTM neural network model construction method for ink drop point error prediction and / or a method for predicting ink drop point error as described above.

[0141] The relevant technical solutions are the same as those in Embodiments 1 and 2, and will not be repeated here.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of ink-jet printing, and particularly discloses a jet printing ink drop point error prediction method which comprises the steps that an LSTM neural network is initialized, network parameters are optimized by adopting an improved double-particle swarm optimization algorithm, a main particle swarm is responsible for integral search, and an auxiliary particle swarm is responsible for diversity search; tent chaotic mapping is adopted to initialize particle swarms and perform local search, so that the diversity and the ergodicity of particle search are improved; an adaptive parameter is adopted to adjust an adaptive strategy, so that the overall and local optimization capacity of the algorithm is enhanced; particle disturbance is carried out by adopting Levy flight, so that the diversity of particles is kept, and a particle swarm is evolved along a better direction; and an LSTM neural network prediction model is established, and the established network prediction model is used for indirect measurement of the jet printing ink drop point error. Compared with an existing trial printing method, the method has the advantages that the printing period is shortened, ink consumption caused by trial printing is avoided, and the method is suitable for being used in application occasions for manufacturing high-resolution displays, electronic components and the like in an ink-jet printing mode.

Description

technical field [0001] The invention belongs to the technical field of inkjet printing, and more particularly relates to a method for predicting errors of ink drop points in jet printing. Background technique [0002] As an emerging OLED manufacturing process, inkjet printing technology has incomparable advantages in terms of material utilization, manufacturing cost, manufacturing size, and manufacturing difficulty compared to traditional vacuum evaporation processes. next-generation mass-manufacturing method. [0003] The premise of the industrial application of inkjet printing technology in the field of OLED manufacturing is high printing accuracy, and the size of the drop point error of ink droplets will directly affect the uniformity and efficiency of the light emitting layer of the high-resolution display. Therefore, how to obtain the drop point error of inkjet printing to compensate for it has become one of the main challenges faced by inkjet printing technology as an...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08B41J2/01
CPCG06N3/08B41J2/01G06N3/044G06F18/214Y02T10/40
Inventor 陈建魁尹周平熊镜凯朱红孔德义
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap